State Estimation and Localization for Self-Driving Cars
- 4.7
-
![]()
![]()
![]()
![]()
![]()
Approx. 27 hours to complete
Course Summary
This course covers state estimation and localization in self-driving cars, including different sensors and algorithms used for accurate positioning.Key Learning Points
- Learn about different sensors used in self-driving cars
- Understand the different algorithms used for accurate positioning
- Get hands-on experience with real-world datasets
Job Positions & Salaries of people who have taken this course might have
- Self-driving car engineer
- USA: $120,000 - $210,000
- India: ₹1,500,000 - ₹2,500,000
- Spain: €40,000 - €70,000
- Localization engineer
- USA: $90,000 - $150,000
- India: ₹1,200,000 - ₹2,000,000
- Spain: €30,000 - €50,000
- Sensor fusion engineer
- USA: $100,000 - $160,000
- India: ₹1,300,000 - ₹2,100,000
- Spain: €35,000 - €55,000
Related Topics for further study
Learning Outcomes
- Understand the basics of state estimation and localization
- Learn how different sensors are used for accurate positioning
- Develop skills to analyze and interpret real-world datasets
Prerequisites or good to have knowledge before taking this course
- Basic knowledge of linear algebra and calculus
- Experience with programming in Python
Course Difficulty Level
IntermediateCourse Format
- Online self-paced
- Video lectures
- Hands-on projects
Similar Courses
- Sensor Fusion and Non-linear Filtering for Automotive Systems
- Self-Driving Cars
Related Education Paths
Notable People in This Field
- CEO of 3D Robotics
- CEO of Kitty Hawk Corporation
Related Books
Description
Welcome to State Estimation and Localization for Self-Driving Cars, the second course in University of Toronto’s Self-Driving Cars Specialization. We recommend you take the first course in the Specialization prior to taking this course.
Knowledge
- Understand the key methods for parameter and state estimation used for autonomous driving, such as the method of least-squares
- Develop a model for typical vehicle localization sensors, including GPS and IMUs
- Apply extended and unscented Kalman Filters to a vehicle state estimation problem
- Apply LIDAR scan matching and the Iterative Closest Point algorithm
Outline
- Module 0: Welcome to Course 2: State Estimation and Localization for Self-Driving Cars
- Welcome to the Self-Driving Cars Specialization!
- Welcome to the Course
- Meet the Instructor, Jonathan Kelly
- Meet the Instructor, Steven Waslander
- Meet Diana, Firmware Engineer
- Meet Winston, Software Engineer
- Meet Andy, Autonomous Systems Architect
- Meet Paul Newman, Founder, Oxbotica & Professor at University of Oxford
- The Importance of State Estimation
- Course Prerequisites: Knowledge, Hardware & Software
- How to Use Discussion Forums
- How to Use Supplementary Readings in This Course
- Module 1: Least Squares
- Lesson 1 (Part 1): Squared Error Criterion and the Method of Least Squares
- Lesson 1 (Part 2): Squared Error Criterion and the Method of Least Squares
- Lesson 2: Recursive Least Squares
- Lesson 3: Least Squares and the Method of Maximum Likelihood
- Lesson 1 Supplementary Reading: The Squared Error Criterion and the Method of Least Squares
- Lesson 2 Supplementary Reading: Recursive Least Squares
- Lesson 3 Supplementary Reading: Least Squares and the Method of Maximum Likelihood
- Lesson 1: Practice Quiz
- Lesson 2: Practice Quiz
- Module 1: Graded Quiz
- Module 2: State Estimation - Linear and Nonlinear Kalman Filters
- Lesson 1: The (Linear) Kalman Filter
- Lesson 2: Kalman Filter and The Bias BLUEs
- Lesson 3: Going Nonlinear - The Extended Kalman Filter
- Lesson 4: An Improved EKF - The Error State Extended Kalman Filter
- Lesson 5: Limitations of the EKF
- Lesson 6: An Alternative to the EKF - The Unscented Kalman Filter
- Lesson 1 Supplementary Reading: The Linear Kalman Filter
- Lesson 2 Supplementary Reading: The Kalman Filter - The Bias BLUEs
- Lesson 3 Supplementary Reading: Going Nonlinear - The Extended Kalman Filter
- Lesson 4 Supplementary Reading: An Improved EKF - The Error State Kalman FIlter
- Lesson 6 Supplementary Reading: An Alternative to the EKF - The Unscented Kalman Filter
- Module 3: GNSS/INS Sensing for Pose Estimation
- Lesson 1: 3D Geometry and Reference Frames
- Lesson 2: The Inertial Measurement Unit (IMU)
- Lesson 3: The Global Navigation Satellite Systems (GNSS)
- Why Sensor Fusion?
- Lesson 1 Supplementary Reading: 3D Geometry and Reference Frames
- Lesson 2 Supplementary Reading: The Inertial Measurement Unit (IMU)
- Lesson 3 Supplementary Reading: The Global Navigation Satellite System (GNSS)
- Module 3: Graded Quiz
- Module 4: LIDAR Sensing
- Lesson 1: Light Detection and Ranging Sensors
- Lesson 2: LIDAR Sensor Models and Point Clouds
- Lesson 3: Pose Estimation from LIDAR Data
- Optimizing State Estimation
- Lesson 1 Supplementary Reading: Light Detection and Ranging Sensors
- Lesson 2 Supplementary Reading: LIDAR Sensor Models and Point Clouds
- Lesson 3 Supplementary Reading: Pose Estimation from LIDAR Data
- Module 4: Graded Quiz
- Module 5: Putting It together - An Autonomous Vehicle State Estimator
- Lesson 1: State Estimation in Practice
- Lesson 2: Multisensor Fusion for State Estimation
- Lesson 3: Sensor Calibration - A Necessary Evil
- Lesson 4: Loss of One or More Sensors
- The Challenges of State Estimation
- Final Lesson: Project Overview
- Final Project Solution [LOCKED]
- Congratulations on Completing Course 2!
- Lesson 2 Supplementary Reading: Multisensor Fusion for State Estimation
- Lesson 3 Supplementary Reading: Sensor Calibration - A Neccessary Evil
Summary of User Reviews
Find out what reviewers are saying about the State Estimation and Localization for Self-Driving Cars course on Coursera. Learn about the overall quality of the course and discover one key aspect that many users thought was good.Key Aspect Users Liked About This Course
The course has a comprehensive and practical approach to state estimation and localization for self-driving cars.Pros from User Reviews
- Instructors are knowledgeable and provide clear explanations.
- The course materials are well-organized and easy to follow.
- The assignments and quizzes are challenging and engaging.
- The course provides a solid foundation for understanding state estimation and localization.
Cons from User Reviews
- Some users found the course to be too technical and difficult to understand.
- The course could benefit from more hands-on exercises and real-world examples.
- The course pace may be too slow for advanced learners.
- The course is not suitable for beginners with no background in robotics or autonomous systems.
Jonathan Kelly
4.7 Raiting
Deep Learning: Advanced Computer Vision (GANs, SSD, +More!)
- 4.6
-
![]()
![]()
![]()
![]()
![]()
VGG, ResNet, Inception, SSD, RetinaNet, Neural Style Transfer, GANs +More in Tensorflow, Keras, and Python Let me give you a quick rundown of what this course is all about:...
State Estimation and Localization for Self-Driving Cars
- 4.7
-
![]()
![]()
![]()
![]()
![]()
Welcome to State Estimation and Localization for Self-Driving Cars, the second course in University of Toronto’s Self-Driving Cars Specialization. By the end of this course, you will be able to:...
Visual Perception for Self-Driving Cars
- 4.7
-
![]()
![]()
![]()
![]()
![]()
Welcome to Visual Perception for Self-Driving Cars, the third course in University of Toronto’s Self-Driving Cars Specialization. To succeed in this course, you should have programming experience in Python 3....
